• Smart Structures and Systems
• /
• v.22 no.2
• /
• pp.175-183
• /
• 2018

Time-series data often contain one of the most valuable pieces of information in many fields including manufacturing. Because time-series data are relatively cheap to acquire, they (e.g., vibration signals) have become a crucial part of big data even in manufacturing shop floors. Recently, deep-learning models have shown state-of-art performance for analyzing big data because of their sophisticated structures and considerable computational power. Traditional models for a machinery-monitoring system have highly relied on features selected by human experts. In addition, the representational power of such models fails as the data distribution becomes complicated. On the other hand, deep-learning models automatically select highly abstracted features during the optimization process, and their representational power is better than that of traditional neural network models. However, the applicability of deep-learning models to the field of prognostics and health management (PHM) has not been well investigated yet. This study integrates the "residual fitting" mechanism inherently embedded in the wavelet transform into the convolutional neural network deep-learning structure. As a result, the architecture combines a signal smoother and classification procedures into a single model. Validation results from rotor vibration data demonstrate that our model outperforms all other off-the-shelf feature-based models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2833-2850
• /
• 2014

This paper proposes a novel framework for traffic video classification based on chaotic features. First, each pixel intensity series in the video is modeled as a time series. Second, the chaos theory is employed to generate chaotic features. Each video is then represented by a feature vector matrix. Third, the mean shift clustering algorithm is used to cluster the feature vectors. Finally, the earth mover's distance (EMD) is employed to obtain a distance matrix by comparing the similarity based on the segmentation results. The distance matrix is transformed into a matching matrix, which is evaluated in the classification task. Experimental results show good traffic video classification performance, with robustness to environmental conditions, such as occlusions and variable lighting.

• Journal of the Korea Society for Simulation
• /
• v.11 no.4
• /
• pp.15-23
• /
• 2002

As recently the network environment and application services have been more complex and diverse, there has. In this paper we introduce a scheme the extract useful information for network management by analyzing traffic data in user login file. For this purpose we use classification and association rule based on episode concept in data mining. Since login data has inherently time series characterization, convertible data mining algorithms cannot directly applied. We generate virtual transaction, classify transactions above threshold value in time window, and simulate the classification algorithm.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.409-418
• /
• 2021

The land cover map is a very important data that is used as a basis for decision-making for land policy and environmental policy. The land cover map is mapped using remote sensing data, and the classification results may vary depending on the acquisition time of the data used even for the same area. In this study, to overcome the classification accuracy limit of single-period data, multi-series satellite images were used to learn the difference in the spectral reflectance characteristics of the land surface according to seasons on a U-Net model, one of the deep learning algorithms, to improve classification accuracy. In addition, the degree of improvement in classification accuracy is compared by comparing the accuracy of single-period data. Seoul, which consists of various land covers including 30% of green space and the Han River within the area, was set as the research target and quarterly Sentinel-2 satellite images for 2020 were aquired. The U-Net model was trained using the sub-class land cover map mapped by the Korean Ministry of Environment. As a result of learning and classifying the model into single-period, double-series, triple-series, and quadruple-series through the learned U-Net model, it showed an accuracy of 81%, 82% and 79%, which exceeds the standard for securing land cover classification accuracy of 75%, except for a single-period. Through this, it was confirmed that classification accuracy can be improved through multi-series classification.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.461-469
• /
• 2022

This paper presents a novel training data extraction approach using semi-supervised learning (SSL)-based classification without the analyst intervention for time-series land-cover mapping. The SSL-based approach first performs initial classification using initial training data obtained from past images including land-cover characteristics similar to the image to be classified. Reliable training data from the initial classification result are then extracted from SSL-based iterative classification using classification uncertainty information and class labels of neighboring pixels as constraints. The potential of the SSL-based training data extraction approach was evaluated from a classification experiment using unmanned aerial vehicle images in croplands. The use of new training data automatically extracted by the proposed SSL approach could significantly alleviate the misclassification in the initial classification result. In particular, isolated pixels were substantially reduced by considering spatial contextual information from adjacent pixels. Consequently, the classification accuracy of the proposed approach was similar to that of classification using manually extracted training data. These results indicate that the SSL-based iterative classification presented in this study could be effectively applied to automatically extract reliable training data for time-series land-cover mapping.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.872-884
• /
• 2022

With the development of the IoT industry, different types of time series data are being generated in various industries, and it is evolving into research that reproduces and utilizes it through re-integration. In addition, due to data processing speed and issues of the utilization system in the actual industry, there is a growing tendency to compress the size of data when using time series data and integrate it. However, since the guidelines for integrating time series data are not clear and each characteristic such as data description time interval and time section is different, it is difficult to use it after batch integration. In this paper, two integration methods are proposed based on the integration criteria setting method and the problems that arise during integration of time series data. Based on this, integration framework of a heterogeneous time series data was constructed that is considered the characteristics of time series data, and it was confirmed that different heterogeneous time series data compressed can be used for integration and various machine learning.

• Journal of Industrial Technology
• /
• v.29 no.B
• /
• pp.9-15
• /
• 2009

In the case of traditional binary encoding technique, it takes long time to converge the optimal solutions and brings about complexity of the systems due to encoding and decoding procedures. However, the ROGAs (real-coded genetic algorithms) do not require these procedures, and the k-means clustering algorithm can avoid global searching space. Thus, this paper proposes a new approach by using their advantages. The proposed method constructs the multiple predictors using the optimal differences that can reveal the patterns better and properties concealed in non-stationary time series where the k-means clustering algorithm is used for data classification to each predictor, then selects the best predictor. After selecting the best predictor, the cluster centers of the predictor are tuned finely via RCGKA in secondary tuning procedure. Therefore, performance of the predictor can be more enhanced. Finally, we verifies the prediction performance of the proposed system via simulating typical time series examples.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.595-602
• /
• 2009

Fuzzy rules, which represent the behavior of their system, are sensitive to fuzzy clustering techniques. If the classification abilities of such clustering techniques are improved, their systems can work for the purpose more accurately because the capabilities of the fuzzy rules and parameters are enhanced by the clustering techniques. Thus, this paper proposes a new hierarchically structured clustering algorithm that can enhance the classification abilities. The proposed clustering technique consists of two clusters based on correlationship and statistical characteristics between data, which can perform classification more accurately. In addition, this paper uses difference data sets to reflect the patterns and regularities of the original data clearly, and constructs multiple fuzzy systems to consider various characteristics of the differences suitably. To verify effectiveness of the proposed techniques, this paper applies the constructed fuzzy systems to the field of time series prediction, and performs prediction for nonlinear time series examples.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1035-1046
• /
• 2022

This study evaluated the applicability of multi-resolution data fusion for land-cover classification. In the applicability evaluation, a spatial time-series geostatistical deconvolution/fusion model (STGDFM) was applied as a multi-resolution data fusion model. The study area was selected as some agricultural lands in Iowa State, United States. As input data for multi-resolution data fusion, Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat satellite images were used considering the landscape of study area. Based on this, synthetic Landsat images were generated at the missing date of Landsat images by applying STGDFM. Then, land-cover classification was performed using both the acquired Landsat images and the STGDFM fusion results as input data. In particular, to evaluate the applicability of multi-resolution data fusion, two classification results using only Landsat images and using both Landsat images and fusion results were compared and evaluated. As a result, in the classification result using only Landsat images, the mixed patterns were prominent in the corn and soybean cultivation areas, which are the main land-cover type in study area. In addition, the mixed patterns between land-cover types of vegetation such as hay and grain areas and grass areas were presented to be large. On the other hand, in the classification result using both Landsat images and fusion results, these mixed patterns between land-cover types of vegetation as well as corn and soybean were greatly alleviated. Due to this, the classification accuracy was improved by about 20%p in the classification result using both Landsat images and fusion results. It was considered that the missing of the Landsat images could be compensated for by reflecting the time-series spectral information of the MODIS images in the fusion results through STGDFM. This study confirmed that multi-resolution data fusion can be effectively applied to land-cover classification.

• Journal of Biomedical Engineering Research
• /
• v.29 no.4
• /
• pp.329-336
• /
• 2008

Recently, causality analysis of source time series extracted from EEG or MEG signals is becoming of great importance in human brain mapping studies and noninvasive diagnosis of various brain diseases. Two approaches have been widely used for the analyses: one is independent component analysis (ICA), and the other is multiple signal classification (MUSIC). To the best of our knowledge, however, any comparison studies to reveal the difference of the two approaches have not been reported. In the present study, we compared the performance of the two different techniques, ICA and MUSIC, especially focusing on how accurately they can estimate and separate various brain electrical signals such as linear, nonlinear, and chaotic signals without a priori knowledge. Results of the realistic simulation studies, adopting directed transfer function (DTF) and Granger causality (GC) as measures of the accurate extraction of source time series, demonstrated that the MUSIC-based approach is more reliable than the ICA-based approach.